Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- cgato/Thespis-CurtainCall-7b-v0.2.2
|
4 |
+
- mistralai/Mistral-7B-v0.1
|
5 |
+
- tavtav/eros-7b-test
|
6 |
+
- cgato/Thespis-7b-v0.5-SFTTest-2Epoch
|
7 |
+
- NeverSleep/Noromaid-7B-0.4-DPO
|
8 |
+
- NurtureAI/neural-chat-7b-v3-1-16k
|
9 |
+
tags:
|
10 |
+
- mergekit
|
11 |
+
- merge
|
12 |
+
license: cc-by-nc-4.0
|
13 |
+
---
|
14 |
+
# LemonadeRP-4.5.3
|
15 |
+
|
16 |
+
This is a merge of pre-trained language models created by KatyTheCutie
|
17 |
+
|
18 |
+
## Merge Details
|
19 |
+
### Merge Method
|
20 |
+
|
21 |
+
This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base.
|
22 |
+
|
23 |
+
### Models Merged
|
24 |
+
|
25 |
+
The following models were included in the merge:
|
26 |
+
* [cgato/Thespis-CurtainCall-7b-v0.2.2](https://huggingface.co/cgato/Thespis-CurtainCall-7b-v0.2.2)
|
27 |
+
* [tavtav/eros-7b-test](https://huggingface.co/tavtav/eros-7b-test)
|
28 |
+
* [cgato/Thespis-7b-v0.5-SFTTest-2Epoch](https://huggingface.co/cgato/Thespis-7b-v0.5-SFTTest-2Epoch)
|
29 |
+
* [NeverSleep/Noromaid-7B-0.4-DPO](https://huggingface.co/NeverSleep/Noromaid-7B-0.4-DPO)
|
30 |
+
* [NurtureAI/neural-chat-7b-v3-1-16k](https://huggingface.co/NurtureAI/neural-chat-7b-v3-1-16k)
|
31 |
+
|
32 |
+
### Configuration
|
33 |
+
|
34 |
+
The following YAML configuration was used to produce this model:
|
35 |
+
|
36 |
+
```yaml
|
37 |
+
base_model: mistralai/Mistral-7B-v0.1
|
38 |
+
dtype: float16
|
39 |
+
merge_method: task_arithmetic
|
40 |
+
slices:
|
41 |
+
- sources:
|
42 |
+
- layer_range: [0, 32]
|
43 |
+
model: mistralai/Mistral-7B-v0.1
|
44 |
+
- layer_range: [0, 32]
|
45 |
+
model: NeverSleep/Noromaid-7B-0.4-DPO
|
46 |
+
parameters:
|
47 |
+
weight: 0.37
|
48 |
+
- layer_range: [0, 32]
|
49 |
+
model: cgato/Thespis-CurtainCall-7b-v0.2.2
|
50 |
+
parameters:
|
51 |
+
weight: 0.32
|
52 |
+
- layer_range: [0, 32]
|
53 |
+
model: NurtureAI/neural-chat-7b-v3-1-16k
|
54 |
+
parameters:
|
55 |
+
weight: 0.15
|
56 |
+
- layer_range: [0, 32]
|
57 |
+
model: cgato/Thespis-7b-v0.5-SFTTest-2Epoch
|
58 |
+
parameters:
|
59 |
+
weight: 0.38
|
60 |
+
- layer_range: [0, 32]
|
61 |
+
model: tavtav/eros-7b-test
|
62 |
+
parameters:
|
63 |
+
weight: 0.18
|
64 |
+
```
|